aseprite-ai-artist

Overview Schema Source Related Servers Discussions Admin

Validate

validate

Read-only

Lint a sprite against pixel-art rules and report located problems such as off-palette colors, stray pixels, broken outlines, and animation issues before calling it done.

Instructions

Lint a sprite against pixel-art rules and report concrete, located problems. Checks: off-palette colours, orphan/stray pixels, broken or doubled outlines, banding, semi-transparent (soft or resized) pixels, empty layers, untagged frames and uniform frame timing; expect adds per-layer frame ranges and layers that must not overlap. Symmetry and cross-frame volume drift are not checked — judge those with look op 'ascii' and 'filmstrip'. Run this before telling the user a sprite is finished. It answers 'is this actually done' with evidence rather than optimism.

Input Schema

TableJSON Schema

Name	Required	Description
`checks`	No	Omit to run everything.
`expect`	No	The animation contract you already know. Runs independently of `checks`, whenever given: flags art outside a layer's expected frame ranges (or a missing cel inside one), and any frame where two named layers' opaque pixels overlap.
`sprite`	No	Which sprite: its id as '#7' (what every result reports back, and the only unambiguous form — two unsaved documents are both called 'Sprite'), its filename, or its display name. Omit to use the sprite Aseprite has focused.
`strict`	No	Treat style warnings as failures. Use when the user asked for a specific discipline.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`score`	Yes
`passed`	Yes
`sprite`	Yes
`summary`	Yes
`findings`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.4.0Sep 30, 2026

addedInput schema / properties / expect

Added value: +{
+  "additionalProperties": false,
+  "description": "The animation contract you already know. Runs independently of `checks`, whenever given: flags art outside a layer's expected frame ranges (or a missing cel inside one), and any frame where two named layers' opaque pixels overlap.",
+  "properties": {
+    "layerFrames": {
+      "additionalProperties": {
+        "items": {
+          "items": [
+            {
+              "exclusiveMinimum": 0,
+              "type": "integer"
+            },
+            {
+              "exclusiveMinimum": 0,
+              "type": "integer"
+            }
+          ],
+          "maxItems": 2,
+          "minItems": 2,
+          "type": "array"
+        },
+        "type": "array"
+      },
+      "description": "Per layer, the [from,to] frame ranges (1-based, inclusive) it should hold ink in.",
+      "type": "object"
+    },
+    "mustNotOverlap": {
+      "description": "Layer name pairs whose opaque pixels must never intersect on the same frame.",
+      "items": {
+        "items": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "string"
+          }
+        ],
+        "maxItems": 2,
+        "minItems": 2,
+        "type": "array"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedv0.1.6Sep 9, 2026

changedInput schema / properties / sprite / description

Previous value: -"Sprite filename or id. Omit to use the sprite Aseprite has focused."New value: +"Which sprite: its id as '#7' (what every result reports back, and the only unambiguous form — two unsaved documents are both called 'Sprite'), its filename, or its display name. Omit to use the sprite Aseprite has focused."

First observedv0.1.0Sep 8, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint/openWorldHint, so the description carries the disclosure burden, and it does so well: it lists exactly what is inspected, what `expect` enforces, and explicitly states the tool is evidence-based rather than optimistic. It stops short of describing the report shape, but an output schema covers that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core verb and check list, then the exclusion note, then the usage directive. Dense but every sentence carries information; only the closing 'evidence rather than optimism' is mild flourish.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter read-only tool with full schema coverage and an output schema, the description supplies everything needed: what it checks, the `expect` semantics, what it deliberately omits, and when to run it. The main residual gap is the relationship to the sibling 'preflight'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning to the `checks` enum by spelling out what each category (palette, strays, outline, banding, antialiasing, layers, animation) actually detects, plus the `expect` contract semantics. This goes beyond the enum strings alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Lint a sprite against pixel-art rules') and enumerates the exact checks performed (off-palette colours, strays, broken outlines, banding, etc.). It also distinguishes itself from the 'look' op by naming what it does NOT check (symmetry, cross-frame volume drift), so an agent can separate it from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit trigger ('Run this before telling the user a sprite is finished') and routes the uncovered concerns to a named alternative. However it does not differentiate from the sibling 'preflight', which likely overlaps with the 'export_readiness' check — that ambiguity is left unresolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server